Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 851 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 2.7973. Min Range: -2.7973
Max Act: 2.7973. Min Act: -0.1700
Data Index: 979064 (C4 (Web Text))
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.7973. Min Range: -2.7973
Max Act: 2.7654. Min Act: -0.1700
Data Index: 284529 (C4 (Web Text))
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.7973. Min Range: -2.7973
Max Act: 2.7495. Min Act: -0.1700
Data Index: 899547 (C4 (Web Text))
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.7973. Min Range: -2.7973
Max Act: 2.7654. Min Act: -0.1700
Data Index: 210321 (C4 (Web Text))
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.7973. Min Range: -2.7973
Max Act: 2.7495. Min Act: -0.1700
Data Index: 1126704 (C4 (Web Text))
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.7973. Min Range: -2.7973
Max Act: 2.7495. Min Act: -0.1700
Data Index: 470133 (C4 (Web Text))
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.7973. Min Range: -2.7973
Max Act: 2.7335. Min Act: -0.1700
Data Index: 836145 (C4 (Web Text))
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.7973. Min Range: -2.7973
Max Act: 2.7335. Min Act: -0.1700
Data Index: 180013 (C4 (Web Text))
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.7973. Min Range: -2.7973
Max Act: 2.7175. Min Act: -0.1700
Data Index: 1278434 (C4 (Web Text))
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.7973. Min Range: -2.7973
Max Act: 2.7015. Min Act: -0.1700
Data Index: 437151 (C4 (Web Text))
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.7973. Min Range: -2.7973
Max Act: 2.7175. Min Act: -0.1700
Data Index: 367516 (C4 (Web Text))
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.7973. Min Range: -2.7973
Max Act: 2.7175. Min Act: -0.1700
Data Index: 164626 (C4 (Web Text))
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.7973. Min Range: -2.7973
Max Act: 2.6855. Min Act: -0.1700
Data Index: 861647 (C4 (Web Text))
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.7973. Min Range: -2.7973
Max Act: 2.6855. Min Act: -0.1700
Data Index: 489043 (C4 (Web Text))
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.7973. Min Range: -2.7973
Max Act: 2.7015. Min Act: -0.1700
Data Index: 175498 (C4 (Web Text))
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.7973. Min Range: -2.7973
Max Act: 2.7015. Min Act: -0.1700
Data Index: 483906 (C4 (Web Text))
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.7973. Min Range: -2.7973
Max Act: 2.6855. Min Act: -0.1700
Data Index: 227839 (C4 (Web Text))
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.7973. Min Range: -2.7973
Max Act: 2.6855. Min Act: -0.1700
Data Index: 979183 (C4 (Web Text))
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.7973. Min Range: -2.7973
Max Act: 2.6855. Min Act: -0.1700
Data Index: 310326 (C4 (Web Text))
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.7973. Min Range: -2.7973
Max Act: 2.6695. Min Act: -0.1700
Data Index: 316840 (C4 (Web Text))
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #19